Paper provides first theoretical guarantees for hyperbolic space learning.
problem Learning a classifier in hyperbolic space for hierarchical data.
method Efficient algorithm for large-margin hyperplane learning in hyperbolic space.
result The low embedding dimension in hyperbolic space leads to superior classifier learning guarantees.
Develops methods to measure and set function-space learning rates in neural networks.
problem Measuring and optimizing changes in neural network output functions.
method Efficient methods to measure and set function-space learning rates, requiring minimal computational overhead.
result Demonstrates FLeRM (Function-space Learning Rate Matching) for hyperparameter transfer across model scales.
A new method improves semi-supervised learning by handling tasks with different attribute spaces.
problem Existing methods assume tasks share the same attribute space, limiting their applicability.
method Meta-learning approach that embeds labeled and unlabeled data in task-specific spaces using neural networks.
result Improves test performance on tasks with small labeled data using unlabeled and various task data.
Study improves learning algorithms for convex polyhedra in Hilbert spaces.
problem Learning convex polyhedra in Hilbert spaces.
method Proposes an algorithm for learning a polyhedron in a Hilbert space.
result Correctly classifies at least 1-ε of the distribution with high probability.
The paper defines a hypothesis space for deep learning using DNNs.
problem Developing a mathematical framework for deep learning.
method Introducing a Banach space of functions of input variables based on DNNs, proving it's a RKBS, and establishing representer theorems for learning models.
result Solutions to learning problems can be expressed as finite sums of kernel expansions based on training data.
In part \textit{I} we proposed a structure for a general Hypotheses Space H, the Learning Space L(H), which can be employed to avoid \textit{overfitting} when estimating in a complex space with relative shortage of examples. Also, we presented the U-curve property, which can be taken ad…
The paper extends graph-based semi-supervised learning to infinite-dimensional Wasserstein space.
problem Graph-based semi-supervised learning in high-dimensional data.
method Laplace Learning in the Wasserstein space, proving variational convergence and characterizing the Laplace-Beltrami operator.
result Consistent classification performance in high-dimensional settings.
Paper analyzes iterative learning for concept classes and learns half-spaces.
problem Learning concept classes efficiently with iterative learners.
method Analyzes various settings of iterative learning and provides a constructive algorithm for half-spaces.
result Constructive iterative algorithm for learning half-spaces from informant.
Improves few-shot learning for hierarchical data using hyperbolic space.
problem Few-shot class-incremental learning for hierarchical data.
method Contrastive learning in hyperbolic space, Poincaré ball model, hyperbolic contrastive loss, maximum entropy distribution.
result Effective improvement of coarse and fine class accuracies in few-shot conditions.
Optimizes learning Hilbert-Schmidt operators between Sobolev spaces.
problem Statistical limits of learning mappings between infinite-dimensional function spaces.
method Minimax optimal regularization and multilevel training.
result Multilevel kernel operator learning achieves optimal learning rate.
Paper introduces invariance-adapted latent space for contrastive learning.
problem Understanding the effectiveness of contrastive learning in data representation.
method Introduces invariance-adapted latent space and uses Lasso-type metric.
result Contrastive learning with Lasso-type metric can find an invariance-adapted latent space.
The paper explores transferring functions from one data space to another.
problem Approximating a function on a new data set using a learned function from an old data set.
method Transfer learning from one data space to another, focusing on subsets of the target data space.
result Local smoothness of the function and its lifting are related.
New findings on when to use action space exploration in reinforcement learning.
problem Understanding when to use action space exploration over traditional methods.
method Theoretical analysis and empirical testing of simple exploration methods.
result Exploration in action space is preferred when parametric complexity exceeds action space dimensionality and horizon length.
New approach to machine learning optimization using distribution space.
problem Optimization challenges in machine learning with non-convex constraints.
method Relaxation to convex optimization in distribution space, numerical algorithm based on mixture distributions.
result Approximate optimization in distribution space is consistent and effective.
A new framework learns system design using neural features in function space.
problem Learning system design with neural feature extractors.
method Introduces feature geometry in function space, nesting technique for optimal feature approximation.
result Optimal features found from data samples using off-the-shelf architectures and optimizers.
Improved deep learning performance in financial markets by using rank space.
problem High volatility and low signal-to-noise ratio in equity market dynamics.
method Transformed equity market data from name space to rank space, enabling better learning by DNNs.
result DNNs achieve superior performance in statistical arbitrage in rank space compared to name space.
Extends online learning to metric spaces using exponential weights.
problem Online learning in metric spaces.
method Exponentially weighted average forecaster, barycenters, Jensen's inequality, measure contraction property.
result Results in a statistical learning framework.
Deep learning has shown high performances in various types of tasks from visual recognition to natural language processing, which indicates superior flexibility and adaptivity of deep learning. To understand this phenomenon theoretically, we develop a new approximation and estimation error analysis of deep learning wit…
Study shows reinforcement learning algorithm's performance depends on metric space's size.
problem Continuous state and action spaces with metrics.
method Refined analysis of Sinclair et al. (2019) algorithm.
result Regret scales with the zooming dimension, a new parameter capturing near optimal actions.
We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence cl…
Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'. Efforts to overcome this phenomenon often utilize resources poorly, for instance, b…
A new method to learn EBM in latent space for better data modeling.
problem Efficiently modeling data with complex structures.
method Joint learning of latent space EBM and top-down network using maximum likelihood and MCMC sampling.
result Simple EBM in latent space captures data regularities effectively and performs well in generation and anomaly detection.
Study efficient neural operator learning using variation spaces.
problem Operator learning using encoder-decoder neural networks.
method Introduce variation space for nonlinear operators, establish approximation bounds.
result Algebraic approximation and learning rates for polynomially decaying input and output encoding errors.
This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some previous models with space decomposition operations only calibrate the confident pr…
Active learning selects inputs for GPSSM to learn latent states.
problem Optimally learn latent states of a GPSSM through active selection of inputs.
method Use mutual information to select informative inputs; approximate mutual information for GPSSM.
result Effective active learning of GPSSM dynamics in physical systems.
Our work improves VAE latent space clustering by enforcing invariant and equivariant learning.
problem Current VAEs fail to learn invariant and equivariant clusters in latent space.
method We use a mixture model pdf like Gaussian mixtures to enforce deep, group-invariant learning and separate semantic and equivariant variables.
result Our model effectively learns to disentangle invariant and equivariant representations, improving learning rate and image recognition.
Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the associated reproducing kernels are investigated. We also present feature map constructions and several concrete examples of vector-valued RK…
Model learns cancer tissue images onto a low-dimensional space revealing tissue characteristics.
problem Improving cancer diagnosis through high-fidelity digital pathology.
method Deep generative model using PathologyGAN to map real images onto a latent space.
result Latent space encodes morphological characteristics and reveals distinct tissue clusters.
Study benchmarks methods for learning non-Cartesian k-space trajectories and reconstruction.
problem Benchmarking methods for learning non-Cartesian k-space trajectories and reconstruction.
method Comparing PILOT, BJORK, and HybLearn schemes to learn non-Cartesian k-space trajectories and reconstruction.
result HybLearn scheme outperforms other methods in learning and comparing non-Cartesian k-space trajectories and reconstruction.
Applying Q-learning to high-dimensional or continuous action spaces can be difficult due to the required maximization over the set of possible actions. Motivated by techniques from amortized inference, we replace the expensive maximization over all actions with a maximization over a small subset of possible actions sam…
Study uses SGD to learn operators in Hilbert spaces with convergence analysis.
problem Learning operators in general Hilbert spaces with SGD.
method Proposes weak and strong regularity conditions for convergence analysis.
result SGD converges to best linear approximation of nonlinear operators.
Quantum machine learning models can approximate any continuous function.
problem Theoretical understanding of quantum feature maps in machine learning.
method Proving universal approximation property of quantum machine learning models in quantum-enhanced feature spaces.
result Quantum machine learning models are universal approximators of continuous functions.
ZoomRL learns efficient strategies for large state-action spaces using a metric.
problem Handling large state-action spaces in reinforcement learning.
method ZoomRL leverages continuous bandits to adaptively discretize the joint space.
result Achieves worst-case regret of $ ilde{O}(H^{ rac{5}{2}} K^{ rac{d+1}{d+2}})$.
Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of their own actions on the environment and to plan complex action sequences. In this work, we address the problem of learning an agent's action…
Paper proposes a method to improve MCMC sampling for energy-based models.
problem MCMC sampling of energy-based models is often not mixing in high-dimensional data.
method Proposes using a flow-based model as a backbone to correct the energy-based model, enabling mixing in latent space.
result MCMC sampling of the corrected EBM in the latent space mixes well and traverses modes in the data space.
New RL method reduces sample complexity for large policy spaces.
problem Large-scale RL with unknown optimal policies and state/action spaces.
method Introduces eluder dimension for policy space, proving near-optimal sample complexity.
result Near-optimal sample complexity upper bound that depends linearly on eluder dimension.
A new method converts neural networks to function space for scalable sequential learning.
problem Challenges in gradient-based deep learning for sequential data.
method Dual parameterization of neural networks from weight to function space.
result Efficient scaling, knowledge retention, and new data incorporation.
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely. Motivated by applications in computer games, we consider the scenario with discrete-continuous hybrid action space. To handle hybrid action space, previous works either approximate the hyb…
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning. We assume the environment is out of our control, but that the agent …
ResNets learn the geodesic curve in Wasserstein space.
problem Characterize the dynamics of deep residual networks during training.
method Modeling ResNet dynamics using continuity equations and optimal transport.
result ResNets learn the geodesic curve in the Wasserstein space.
We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples learning the transformation from the source language to the target language into (a) learning rotations for language-specific embeddings to align them to a common space, …
We consider a general regularised interpolation problem for learning a parameter vector from data. The well known representer theorem says that under certain conditions on the regulariser there exists a solution in the linear span of the data points. This is at the core of kernel methods in machine learning as it makes…
This paper investigates the notion of learning user and item representations in non-Euclidean space. Specifically, we study the connection between metric learning in hyperbolic space and collaborative filtering by exploring Mobius gyrovector spaces where the formalism of the spaces could be utilized to generalize the m…
This work uses action equivariance to learn structured latent spaces for reinforcement learning.
problem Learning structured latent spaces for reinforcement learning.
method Introduced a contrastive loss function to enforce action equivariance on learned representations.
result Optimal policies in the abstract MDP can be successfully lifted to the original MDP.
Novel metric space magnitude and weighting vectors improve machine learning tasks.
problem Improving machine learning algorithms using novel metric space concepts.
method Metric space magnitude and weighting vectors for better machine learning.
result The weighting vector effectively detects boundaries and improves classic machine learning tasks.
Gradient descent reshapes the function space of neural networks.
problem Understanding how feature learning affects the function space of neural networks.
method Characterized the evolution of the feature space during training using a two-layer neural network.
result Gradient descent induces a data-adaptive deformation that selectively enhances signal-aligned directions.
New method reduces version space for CNNs, improving active learning performance.
problem Sampling bias in active learning hinders optimal hypothesis finding in neural networks.
method Version space reduction through prior mass reduction and diameter reduction, proposing a new Gibbs-vote disagreement method.
result Diameter-based querying method reduces version space more effectively than prior mass reduction and other methods.
New method learns state embeddings from demonstrations for improved reinforcement learning.
problem Difficult relationship between observed state and useful policy actions in dynamic problems.
method Variational framework for learning state embeddings that optimize trajectory linearity.
result Learning embedding spaces improves policy gradient reinforcement learning performance.